3D Building Generation in Minecraft via Large Language Models

Shiying HU, Zengrong HUANG, Chengpeng HU, Jialin LIU*

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

1 Citation (Scopus)

Abstract

Recently, procedural content generation has exhibited considerable advancements in the domain of 2D game level generation such as Super Mario Bros. and Sokoban through large language models (LLMs). To further validate the capabilities of LLMs, this paper explores how LLMs contribute to the generation of 3D buildings in a sandbox game, Minecraft. We propose a Text to Building in Minecraft (T2BM) model, which involves refining prompts, decoding interlayer representation and repairing. Facade, indoor scene and functional blocks like doors are supported in the generation. Experiments are conducted to evaluate the completeness and satisfaction of buildings generated via LLMs. It shows that LLMs hold significant potential for 3D building generation. Given appropriate prompts, LLMs can generate correct buildings in Minecraft with complete structures and incorporate specific building blocks such as windows and beds, meeting the specified requirements of human users.

Original languageEnglish
Title of host publicationProceedings of the 2024 IEEE Conference on Games, CoG 2024
PublisherIEEE Computer Society
Number of pages4
ISBN (Electronic)9798350350678
DOIs
Publication statusPublished - Aug 2024
Externally publishedYes
Event6th Annual IEEE Conference on Games, CoG 2024 - Milan, Italy
Duration: 5 Aug 20248 Aug 2024

Publication series

NameIEEE Conference on Computatonal Intelligence and Games, CIG
ISSN (Print)2325-4270
ISSN (Electronic)2325-4289

Conference

Conference6th Annual IEEE Conference on Games, CoG 2024
Country/TerritoryItaly
CityMilan
Period5/08/248/08/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Funding

This work was supported by the National Key R&D Program of China (Grant No. 2023YFE0106300), the National Natural Science Foundation of China (Grant No. 62250710682), the Guangdong Major Project of Basic and Applied Basic Research (Grant No. 2023B0303000010), the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), and the Research Institute of Trustworthy Autonomous Systems.

Keywords

  • 3D generation
  • building generation
  • LLMs
  • Minecraft
  • Procedural content generation

Fingerprint

Dive into the research topics of '3D Building Generation in Minecraft via Large Language Models'. Together they form a unique fingerprint.

Cite this